Resolution invariant wavelet features of melanoma studied by SVM classifiers.
This article refers to the Computer Aided Diagnosis of the melanoma skin cancer. We derive wavelet-based features of melanoma from the dermoscopic images of pigmental skin lesions and apply binary C-SVM classifiers to discriminate malignant melanoma from dysplastic nevus. The aim of this research is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0211318 |
| _version_ | 1818938768724328448 |
|---|---|
| author | Grzegorz Surówka Maciej Ogorzalek |
| author_facet | Grzegorz Surówka Maciej Ogorzalek |
| author_sort | Grzegorz Surówka |
| collection | DOAJ |
| description | This article refers to the Computer Aided Diagnosis of the melanoma skin cancer. We derive wavelet-based features of melanoma from the dermoscopic images of pigmental skin lesions and apply binary C-SVM classifiers to discriminate malignant melanoma from dysplastic nevus. The aim of this research is to select the most efficient model of the SVM classifier for various image resolutions and to search for the best resolution-invariant wavelet bases. We show AUC as a function of the wavelet number and SVM kernels optimized by the Bayesian search for two independent data sets. Our results are compatible with the previous experiments to discriminate melanoma in dermoscopy images with ensembling and feed-forward neural networks. |
| first_indexed | 2024-12-20T06:13:06Z |
| format | Article |
| id | doaj.art-91db413c64ec417aa9558cd24f5cbeee |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-20T06:13:06Z |
| publishDate | 2019-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-91db413c64ec417aa9558cd24f5cbeee2022-12-21T19:50:36ZengPublic Library of Science (PLoS)PLoS ONE1932-62032019-01-01142e021131810.1371/journal.pone.0211318Resolution invariant wavelet features of melanoma studied by SVM classifiers.Grzegorz SurówkaMaciej OgorzalekThis article refers to the Computer Aided Diagnosis of the melanoma skin cancer. We derive wavelet-based features of melanoma from the dermoscopic images of pigmental skin lesions and apply binary C-SVM classifiers to discriminate malignant melanoma from dysplastic nevus. The aim of this research is to select the most efficient model of the SVM classifier for various image resolutions and to search for the best resolution-invariant wavelet bases. We show AUC as a function of the wavelet number and SVM kernels optimized by the Bayesian search for two independent data sets. Our results are compatible with the previous experiments to discriminate melanoma in dermoscopy images with ensembling and feed-forward neural networks.https://doi.org/10.1371/journal.pone.0211318 |
| spellingShingle | Grzegorz Surówka Maciej Ogorzalek Resolution invariant wavelet features of melanoma studied by SVM classifiers. PLoS ONE |
| title | Resolution invariant wavelet features of melanoma studied by SVM classifiers. |
| title_full | Resolution invariant wavelet features of melanoma studied by SVM classifiers. |
| title_fullStr | Resolution invariant wavelet features of melanoma studied by SVM classifiers. |
| title_full_unstemmed | Resolution invariant wavelet features of melanoma studied by SVM classifiers. |
| title_short | Resolution invariant wavelet features of melanoma studied by SVM classifiers. |
| title_sort | resolution invariant wavelet features of melanoma studied by svm classifiers |
| url | https://doi.org/10.1371/journal.pone.0211318 |
| work_keys_str_mv | AT grzegorzsurowka resolutioninvariantwaveletfeaturesofmelanomastudiedbysvmclassifiers AT maciejogorzalek resolutioninvariantwaveletfeaturesofmelanomastudiedbysvmclassifiers |